Unsupervised learning of rules for morphological disambiguation

Abstract

State-of-the-art rule-based tools for morphological disambiguation use either manually crafted rules or rules learnt from manually annotated data. This paper presents a new method of learning rules for morphological disambiguation using only unannotated data. The inductive logic programming and active learning are employed. The induced rules display very promising acurracy. Also the probable limitations of the proposed method are discussed. © Springer-Verlag Berlin Heidelberg 2004.